Hy3

tencent· 2026-07-06· 262K ctx· apache-2.0

open weightstool callreasoningstructured quant: unknown

spread (output)

2.5×

$0.260 – $0.640 · 9 providers

9 providers priced

Provider	Input	Output	Cache rd	Blended
NanoGPT relay router	$0.066	$0.260	$0.029	$0.060
LLM Gateway relay router	$0.132	$0.528	$0.033	$0.105
OpenRouter unknown	$0.132	$0.528	$0.033	$0.105
Kilo Gateway relay router	$0.132	$0.528	$0.033	$0.105
Vercel AI Gateway unknown	$0.140	$0.580	$0.035	$0.113
Deep Infra open weights host	$0.140	$0.580	$0.035	$0.113
Hugging Face relay router	$0.140	$0.580	—	$0.180^*
OrcaRouter relay router	$0.180	$0.590	$0.059	$0.140
CrossModel relay router	$0.160	$0.640	$0.040	$0.140

Cheapest (output)

NanoGPT

$0.260 /M

opencode.json

{
  "provider": {
    "nano-gpt": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://nano-gpt.com/api/v1"
      },
      "models": {
        "tencent/hy3": {}
      }
    }
  }
}

Set NANO_GPT_API_KEY in your environment. Generated — verify against the OpenCode docs.

Output $/M over time7-day preview

Median line, min–max band. Pre-2026-09 points are catalog-recorded dates from models.dev git history, not provider effective dates.

Full price history & dynamics

This is a 7-day preview. Sign in for 30 days free; the full series and export are the API subscription.

Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.